- Well for me, kind of a IT jack of all trades, a little programming, a little server management, a little DBA, HTML, Network and domain shat, etc, yeah a little bit of everything under my belt. I am finding Cursor incredibly enabling. You have heard it here before I know but I really wish I had this when I was in the trenches. I am retired now. I use it for various little programs I am writing and one big project. I use Cursor with opus 4.5 mostly, and finding that none of my questions and none of my requests have hit a brick wall, some walls for sure but not the kind of brick walls I would run into in the past where I would have no one to turn to immediately and those that I could turn to were also busy very busy with their s**, sometimes taking hours to get through to them or maybe even days. All that's gone. With the help of AI I can usually work out any kind of problem I have. Now, as for the quality of the code, well that may be another story. It might be twice as much as any , more experienced programmer might write but so far, with my experience, I have not seen anything that looks untoward.
Bottom line is that I am extremely grateful for AI has a teammate. As a solopreneur even more so. I'm building an application that I know would have taken at least $10 to 20K to build but all I'm paying is $60 a month Cursor Pro+ and my public facing server. And only $60 because I ran into a Cursor Claude limit.
Buckle up guys and gals, the midwit you always feared has the keys to the tank now...
by dudewhocodes
15 subcomments
- > I am at the tail end of AI adoption, so I don’t expect to say anything particularly useful or novel.
Are they really late? Has everyone started using agents and paying $200 subscriptions?
Am I the one wrong here or these expressions of "falling behind" are creating weird FOMO in the industry?
EDIT: I see the usefulness of these tools, however I can't estimate how many people use them.
- TS + Deno + dax is my favorite scripting environment. (Bun has a similar $ function built in.) For parsing CLI args, I like the builders from Cliffy (https://cliffy.io/) or Commander.js because you get typed options objects and beautiful help output for free.
If you want to script in Rust, xshell (https://docs.rs/xshell/latest/xshell/) is explicitly inspired by dax.
by erdaniels
1 subcomments
- Hey ibobev! I've actually been building something very close to box at a snail's pace for 2 years. I built it since I was working a lot with a bunch of raspberry pis where it was better to compile directly on the pi then on my mac but I didn't want to bother to ssh in or lose my local setup. The major difference with what I have so far is that the tool takes a direnv automagical approach to work with multiple machines across multiple projects/directories. It works across docker and ssh without any extra setup other than the tool on the client side.
I just got native LSP working this past weekend and in sublime it's as much as:
{
"clients":
{
"remote-gopls":
{
"command":
[
"tool",
"lsp",
"gopls"
],
"enabled": false,
"selector": "source.go",
},
}
}
From what you built so far, do you think there's any appetite in people paying for this type of tool which lets you spin up infra on demand and gives you all the capabilities built so far? I'm skeptical and I may just release it all as OSS when it gets closer to being v1.0.
by liampulles
0 subcomment
- Thank you to OP for writing a "LLM assisted coding" usage report which feels humble and honest. I'm in an evaluation phase myself and I find it very difficult to find good evaluations from typical developers.
- I bought a glm-4.7 subscription and paired it with with claude code. According to usage, I have already used millions of tokens, yet I have barely reached the prompt limits for the tier I have per the 5 hour window. I haven't done anything crazy with my prompts as well.
Now if this were something else billed per 1 million tokens it would have cost me a lot more.
Yet apparently the majority of LLM providers are billing for 1 million tokens.
What's the catch? What I am not understanding? What other providers have similar usage/pricing pattern?
I can't see any of the providers billing per 1 million tokens to be useful/cost effective at all for coding.
Granted, I am new to all of this, I want to see what the fuss is about so perhaps I am blind to something obvious.
by jasonjmcghee
1 subcomments
- Any time doing hand-rolled on demand spinning up of ec2 instances, be sure they are properly spun down later.
It's very easy to get hit with a massive bill due to just leaving instances around.
- @gtowey I think it was basically a lack of ability to focus for myriad distractions in my life, suboptimal upbringing, family obligations, I think I'm a little dyslexic, larger career obligations, top of everything else I had a career in the reserves also that's where a lot of my energy went primetime, also being a musician I found it a lot easier to play a musical instrument than spend the time needed develop chops programming wise. and then there's my family, lot of time spent focused on them. A lot of distractions on top of a pretty poor memory basically. I can say all that stuff now cuz I'm yes an entrepreneur but I'm also retired. It might actually boil down to a lack of discipline. But who knows, Tell you one thing for sure I am totally getting off on AI assisted programming. Any question I have, there's an answer that fits within my understanding of the way things work which is not minimal with all my experience in IT so whatever it is it's working.
by cadamsdotcom
0 subcomment
- Love this. People making their own tools for their own problems.
Author needed a thing, it didn’t exist, so they made that thing.
That’s incredible empowerment.
- I've been meaning to try programming with AI, but it's a bit tricky to manage the maze of models which one can download and run. I know one can pull down qwen3 or starcoder2 with ollama, but there's multiple variations and I have no idea what everything means and what the implications are for running them on my PC. I suppose cloud-based offers simplify all that, but I don't trust them for a hair.
by css_apologist
1 subcomments
- this isn't technically vibe coding right? this is just like using llms here and there for details you don't care to learn more about
- > The spec ended up being 6KiB of English prose. The final implementation was 14KiB of TypeScript.
Wait, this is how people vibe code? I thought it was just giving instruction line by line and refining your program. People are really creating a dense, huge spec for their project first?
I have not seen any benefit of AI in programming yet, so maybe I should try it with specs and like a auto-complete as well.
- Nice write up but one thing that irks me..
> I personally don’t know how to solve it without wasting a day. So, I spent a day vibecoding my own square wheel.
This worries me, in the case of OP it seems was dillegent and reviewed everything thoroughly but I can bet that that's not the majority.. And pushing to prod an integral piece without fully knowing how it works just terrifies me.
by wiredfool
2 subcomments
- Capistrano?
Fabric?
- It feels like gnu parallel with --transfer-file would have solved this problem
by yakshaving_jgt
0 subcomment
- The only way I would approach a problem like this is with NixOS and nixosTest/runTest. Development iterations can be against local VMs, and then you can fire it at AWS when you're confident it works correctly.
- I wish I could be slightly more interested in this to actually see what payoff this person is reporting here but I just can't bring myself to care about this agentic nonsense.
by jacobtomlinson
1 subcomments
- Instructions unclear, Claude just spent three days and millions of tokens rebuilding SLURM from the ground up. /s
by indigodaddy
1 subcomments
- This is excellent and innovative, good stuff! I guess my only comment is why not just Ansible, but this feels like a way simpler and better fit (and more fun/cool! Plus you can just easily modify/bend the tool to your liking/need) just for playing around in your local homelab etc
Hacker News